Connecting a model via OpenRouter

OpenRouter is a platform that allows you to connect to various AI models and use them for text generation or other tasks.

To connect a model via OpenRouter, follow these steps:

1. Go to https://openrouter.ai/, sign up, and create your own API key.

2. Return to our site and go to the “Models” tab. Click “Add Host”.

   
3. In the “Endpoint URL” field, enter: https://openrouter.ai/api/v1/chat/completions. In the “Access Token” field, paste your generated key. Click “Create Host”.

   
4. Return to our site, go to the model catalog, and select the “Hosts” tab. Click “Add Host.”

   
5. In the “Host” field, select the host you created earlier. In “Display Name,” enter the name that will be shown in the catalog. In “Model Name,” enter the exact model name from the OpenRouter site (for example: mistralai/mistral-7b-instruct). In “Description,” describe the model’s strengths and weaknesses.

   
6. Below, specify the maximum context size, privacy settings, one or more functionality tags, and additional settings supported by the model.

   
7. Click “Create Model” to create the model. Wait a moment, and the model will appear in the list.